Face illumination processing via dense feature maps and multiple receptive fields

Recently, illumination processing of facial image based on generative adversarial networks has made favourable progress. However, the image quality is not so satisfactory and the recognition accuracy is low when the face image under extreme illumination conditions. For these reasons, an elaborately‐...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Electronics letters Ročník 57; číslo 16; s. 627 - 629
Hlavní autoři: Ling, Shenggui, Fu, Keren, Lin, Ye, You, Di, Cheng, Peng
Médium: Journal Article
Jazyk:angličtina
Vydáno: Stevenage John Wiley & Sons, Inc 01.08.2021
Wiley
Témata:
Accuracy
Artificial neural networks
Coders
Computer vision and image processing techniques
Feature maps
Generative adversarial networks
Identification
Illumination
Image and video coding
Image quality
Image recognition
Methods
Neural nets
Performance evaluation
ISSN:0013-5194, 1350-911X
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Recently, illumination processing of facial image based on generative adversarial networks has made favourable progress. However, the image quality is not so satisfactory and the recognition accuracy is low when the face image under extreme illumination conditions. For these reasons, an elaborately‐designed architecture based on convolutional neural network and generative adversarial networks for processing face illumination is presented. A novel dense feature maps loss that computes loss by using the varisized feature maps extracted from different convolutional layers of pre‐trained feature network is put forward. Moreover, multiple‐receptive‐fields‐based generator that uses multiple encoders during encoding phase is also proposed, and these encoders have the same structure with different kernel size. A variety of experimental results demonstrate that the method is superior to the state‐of‐the‐art methods under various illumination challenges. Code will be available soon at https://github.com/ling20cn/IP‐GAN
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0013-5194
1350-911X
DOI:10.1049/ell2.12181